期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：75
期号：2
出版社：Journal of Theoretical and Applied
摘要：In this paper we proposed a method which avoids the choice of natural language processing tools such as pos taggers and parsers reduce the processing overhead. Moreover, we suggest a structure to immediately create a large-scale corpus annotated along with disease names, which can be applied to train our probabilistic model. In this proposed work context rank based hierarchical clustering method is applied on different datasets namely colon, Leukemia, MLL, Lymphoma medical diseases. Optimal rule filtering algorithm is applied on these datasets to remove unwanted special characters for gene/protein identification. Finally, experimental results show that proposed method outperformed existing methods in terms of time and clusters space.
